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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47557
    Prev
    Next
    INDEX
    Explanations

    coping strategies

    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
    ahui
    -0.09
    ทธิ
    -0.09
     utilized
    -0.09
     didn't
    -0.08
     votes
    -0.08
    n't
    -0.08
     عدم
    -0.08
     ছাড়া
    -0.08
     નહિ
    -0.08
     არა
    -0.08
    POSITIVE LOGITS
     gush
    0.13
     indulge
    0.13
     obsess
    0.13
     waffle
    0.12
     harp
    0.12
     joke
    0.11
     bab
    0.11
     ramb
    0.11
     fetish
    0.11
     cling
    0.11
    Activations Density 0.097%

    No Known Activations