Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 119324
    Prev
    Next
    INDEX
    Explanations

    PR/relations

    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
     MPG
    -0.09
     liefert
    -0.08
     lactose
    -0.08
     IRS
    -0.08
     Carmel
    -0.08
    ungen
    -0.08
     jugadores
    -0.08
     Händler
    -0.08
     Spieler
    -0.08
     LDL
    -0.08
    POSITIVE LOGITS
    /social
    0.09
     relações
    0.08
    -служ
    0.08
     outreach
    0.08
     booster
    0.08
    关系
    0.08
     stunt
    0.08
     �
    0.08
     라이
    0.08
     вступ
    0.08
    Activations Density 0.010%

    No Known Activations