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. 1749
    Prev
    Next
    INDEX
    Explanations

    given specified

    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
    -benef
    -0.07
     wodurch
    -0.07
     Pele
    -0.07
     തേ
    -0.07
     самого
    -0.07
     часу
    -0.07
     hired
    -0.07
    Gra
    -0.07
    Kel
    -0.07
     Каж
    -0.07
    POSITIVE LOGITS
    स्था
    0.09
    .protocol
    0.08
    �
    0.08
    扶
    0.07
     bà
    0.07
     garg
    0.07
    bí
    0.07
    xfd
    0.07
     macam
    0.07
     MSM
    0.07
    Activations Density 0.022%

    No Known Activations