© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49124
    Prev
    Next
    INDEX
    Explanations

    string conversion

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CGRect
    -0.07
    .Contains
    -0.07
     minlength
    -0.07
     beë
    -0.07
     стоп
    -0.07
    ætter
    -0.07
    ecycle
    -0.07
    ’avenir
    -0.07
    .contains
    -0.07
     divide
    -0.07
    POSITIVE LOGITS
    .to
    0.28
    .To
    0.26
    _str
    0.25
    Str
    0.23
    String
    0.23
    _string
    0.22
     tostring
    0.22
    .stringify
    0.21
    _repr
    0.21
    _STRING
    0.21
    Activations Density 0.036%

    No Known Activations