© 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. 23-RESID-POST-AA
    11. 6304
    Prev
    Next
    INDEX
    Explanations

    SUB

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     凤
    -0.09
     衡
    -0.09
    ointments
    -0.09
    .grp
    -0.08
    amız
    -0.08
     �
    -0.08
    áz
    -0.08
    -kan
    -0.08
     kaynak
    -0.08
     төл
    -0.08
    POSITIVE LOGITS
    urban
    0.11
    UR
    0.10
    urbs
    0.09
    urb
    0.09
    URU
    0.09
     suburban
    0.08
    ur
    0.08
     urbano
    0.08
    urwa
    0.08
    Pr
    0.08
    Activations Density 0.001%

    No Known Activations