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. 7-RESID-POST-AA
    6. 1820
    Prev
    Next
    INDEX
    Explanations

    Slowly changing dimensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /pi
    -0.08
    های
    -0.08
    preced
    -0.08
    喷
    -0.07
    Iyo
    -0.07
    ogonal
    -0.07
    Harness
    -0.07
    Prere
    -0.07
    �
    -0.07
    好运
    -0.07
    POSITIVE LOGITS
    ald
    0.08
     booth
    0.08
    coa
    0.08
    iculum
    0.07
     captain
    0.07
    amac
    0.07
    inius
    0.07
     klas
    0.07
     immortal
    0.07
     выяв
    0.07
    Activations Density 0.000%

    No Known Activations