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. 44252
    Prev
    Next
    INDEX
    Explanations

    Clinical trials

    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
    IEL
    -0.08
     theological
    -0.08
    149
    -0.07
    werken
    -0.07
    OTS
    -0.07
    -0.07
    atsi
    -0.07
    unte
    -0.07
    621
    -0.07
    efi
    -0.07
    POSITIVE LOGITS
     placebo
    0.12
     randomized
    0.10
     challenger
    0.10
     blinded
    0.08
     വിതരണം
    0.08
     таблетки
    0.08
     transt
    0.08
     bracelet
    0.08
     opdrachtgever
    0.08
     മണ്ഡ
    0.08
    Activations Density 0.004%

    No Known Activations