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. 43419
    Prev
    Next
    INDEX
    Explanations

    pea

    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
    _perm
    -0.08
    HL
    -0.08
     implying
    -0.08
    mul
    -0.08
    เฉ
    -0.08
    fi
    -0.07
    vertr
    -0.07
     NGO
    -0.07
    Harry
    -0.07
    UB
    -0.07
    POSITIVE LOGITS
    -hole
    0.08
     Dan
    0.08
     �
    0.07
    inte
    0.07
     nub
    0.07
    0.07
     �
    0.07
    corn
    0.07
     Nob
    0.07
     прин
    0.07
    Activations Density 0.015%

    No Known Activations