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. 42122
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    exports
    -0.08
    VEL
    -0.08
    vel
    -0.08
    Dur
    -0.08
    JOY
    -0.07
     এল
    -0.07
     amistad
    -0.07
     एल
    -0.07
    Aceptar
    -0.07
     Ciudad
    -0.07
    POSITIVE LOGITS
     hingegen
    0.09
    ,X
    0.08
     Wow
    0.07
    ,Q
    0.07
     [],
    0.07
    ,N
    0.07
    ,item
    0.07
    :X
    0.07
     ???↵↵
    0.07
    ahar
    0.07
    Activations Density 0.069%

    No Known Activations