© 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. 11-RESID-POST-AA
    11. 8029
    Prev
    Next
    INDEX
    Explanations

    tangible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    त्र
    -0.10
     sobie
    -0.09
     tandem
    -0.08
    Possible
    -0.08
     �
    -0.08
    Ses
    -0.08
     possible
    -0.08
     retros
    -0.08
     ceremon
    -0.08
     يجوز
    -0.08
    POSITIVE LOGITS
     concr
    0.09
     ощ
    0.09
    מח
    0.08
     affection
    0.08
     Leib
    0.08
     concret
    0.07
     apre
    0.07
    abot
    0.07
     attente
    0.07
     ẹni
    0.07
    Activations Density 0.005%

    No Known Activations