© 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. 19-RESID-POST-AA
    11. 103013
    Prev
    Next
    INDEX
    Explanations

    pandas dataframe code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parameter
    -0.09
    .Parameter
    -0.08
    .Parameters
    -0.08
     Parameter
    -0.08
    参数
    -0.08
     "
    -0.07
     implement
    -0.07
    Operator
    -0.07
    Parameters
    -0.07
    (Parameter
    -0.07
    POSITIVE LOGITS
     Suppose
    0.14
     suppose
    0.13
    sample
    0.12
     Assume
    0.11
     dữ
    0.11
    Supp
    0.11
     datos
    0.10
    data
    0.10
     supon
    0.10
     dados
    0.10
    Activations Density 0.079%

    No Known Activations