Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 114000
    Prev
    Next
    INDEX
    Explanations

    technology and software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wollen
    -0.08
    ********************************************************
    -0.08
    EUR
    -0.07
    nhof
    -0.07
    *******************************************************************************↵
    -0.07
    ٓ
    -0.07
    ृह
    -0.07
    -0.07
    CAE
    -0.07
     pensa
    -0.07
    POSITIVE LOGITS
     nuevamente
    0.09
     novamente
    0.09
     leggere
    0.08
     опять
    0.08
     again
    0.08
     randint
    0.07
    Again
    0.07
     Again
    0.07
     Fun
    0.07
     hierfür
    0.07
    Activations Density 0.419%

    No Known Activations