© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 103325
    Prev
    Next
    INDEX
    Explanations

    2

    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
    ისა
    -0.09
    ებისა
    -0.09
    ijining
    -0.09
     nende
    -0.09
    zisa
    -0.09
    ities
    -0.08
     umz
    -0.08
    lerini
    -0.08
     semelh
    -0.08
     luchd
    -0.08
    POSITIVE LOGITS
    _RELEASE
    0.08
    _Open
    0.08
    _From
    0.08
     verwenden
    0.08
    _OPEN
    0.08
    _WAKE
    0.08
    _With
    0.08
    _Enable
    0.08
     whether
    0.08
    .startswith
    0.08
    Activations Density 0.001%

    No Known Activations