© 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. 96872
    Prev
    Next
    INDEX
    Explanations

    say "p" words

    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
     reutil
    -0.09
    ժ
    -0.09
     Fauc
    -0.08
     guud
    -0.08
    روف
    -0.08
     Skilled
    -0.08
    友情链接
    -0.08
    landır
    -0.08
     Juni
    -0.08
     الزرا
    -0.08
    POSITIVE LOGITS
     واضح
    0.08
    her
    0.08
     reveal
    0.08
    ier
    0.08
    Alors
    0.08
    anz
    0.07
    Puis
    0.07
    _the
    0.07
     aan
    0.07
    oter
    0.07
    Activations Density 0.001%

    No Known Activations