© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2675
    Prev
    Next
    INDEX
    Explanations

    Officer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mening
    -0.09
    NF
    -0.08
    KV
    -0.08
    ziehung
    -0.08
    220
    -0.08
    ంలోని
    -0.07
    980
    -0.07
    -ci
    -0.07
     exped
    -0.07
    _ci
    -0.07
    POSITIVE LOGITS
     Agnes
    0.08
    াৎ
    0.08
     omn
    0.08
     incl
    0.07
     blender
    0.07
     fisheries
    0.07
     ferm
    0.07
     lyn
    0.07
     mamm
    0.07
     документа
    0.07
    Activations Density 0.004%

    No Known Activations